Martin Forst
|
Mailing address:
Powerset, Inc
475 Brannan St.
San Francisco, CA 94304 USA
|
|
|
|
Office/Contact:
email: Martin.Forst "at" microsoft
"dot" com
|
Bio
Martin Forst joined PARC
in 2007. He was a member of the research staff in the Natural Language
Theory and Technology area of the Intelligent Systems
Laboratory.
Martin received his Ph.D.
in Computational Linguistics from the Institute
for Natural Language Processing of the University
of Stuttgart (Germany). The focus of his work lies on grammar engineering
(in LFG), especially the
combination of "deep" linguistic processing techniques with empirical
methods. He is part of the Parallel Grammar (ParGram) project, a joint initiative with
university and industry sites around the world that builds broad-coverage,
industrial-strength LFG grammars using the XLE
parser/generator/rewrite system. The English ParGram grammar
is used by Powerset/Microsoft
for
consumer search and in the Ambiguity-enabled,
Scalable Knowledge Repository project. Together with the German and the Chinese ParGram grammars, it is also used
for a pilot project in grammar-based machine translation that Martin and
colleagues work on.
Since summer 2007, Martin has been serving as a
program committee chair of the International Lexical Functional Grammar
Association (ILFGA). He
joined the Powerset group in Microsoft in 2009.
Publications
2007
- Cahill, Aoife, Martin Forst & Christian Rohrer (2007):
Stochastic Realisation Ranking for a Free Word
Order Language. In Busemann, S. (ed.): Proceedings of the European Workshop on
Natural Language Generation (ENLG-07), Dagstuhl
(Germany). PDF,
8 pages.
- Forst, Martin
(2007): Filling Statistics with Linguistics - Property Design for the
Disambiguation of German LFG Parses. In Proceedings of the ACL Workshop on Deep Linguistic Processing,
Prague (Czech Republic). PDF, 8 pages.
2006
- Forst, Martin
& Ronald M. Kaplan (2006): The importance of precise tokenizing for
deep grammars. In Proceedings of the
5th Conference on Language Resources and Evaluation (LREC 2006), Genoa
(Italy). PDF,
8 pages.
- Rohrer, Christian
& Martin Forst (2006): Improving coverage and parsing quality of a
large-scale LFG for German. In Proceedings
of the 5th Conference on Language Resources and Evaluation (LREC 2006),
Genoa (Italy). PDF,
8 pages.
- Rohrer, Christian
& Martin Forst (2006): Hand-crafted grammar
development - How far can it go? In Butt, M., M. Dalrymple
and T. H. King (eds.): Intelligent
Linguistic Architectures - Variations on Themes by Ronald M. Kaplan,
CSLI Publications, Stanford (California).
- Forst, Martin
(2006): COMP in (Parallel) Grammar Writing. Proceedings
of the LFG06 Conference, Constance (Germany). PDF, 18 pages.
2005
- Cahill, Aoife, Martin Forst, Michael Burke, Mairéad McCarthy, Ruth O'Donovan, Christian Rohrer,
Josef van Genabith & Andy Way (2005):
Treebank-Based Acquisition of Multilingual Unification Grammar Resources.
In Bender, E., D. Flickinger, F. Fouvry and M. Siegel (eds.): Journal of Research on Language and Computation; Special Issue on
"Shared Representations in Multilingual Grammar Engineering",
Kluwer Academic Press, pages 247 - 279.
- Forst, Martin,
Jonas Kuhn & Christian Rohrer (2005): Corpus-based learning of OT
constraint rankings for large-scale LFG grammars. In Proceedings
of the LFG05 Conference, Bergen (Norway). PDF,
12 pages.
- King, Tracy H.,
Martin Forst, Jonas Kuhn & Miriam Butt
(2005): The Feature Space in Parallel Grammar Writing. In Bender, E., D. Flickinger, F. Fouvry and M.
Siegel (eds.): Journal of Research
on Language and Computation; Special Issue on
"Shared Representations in Multilingual Grammar Engineering",
Kluwer Academic Press.
- Siebenhaar, Beat, Martin Forst & Eric Keller
(2005): Speech synthesis of dialectal variants as a method for research on
prosody. In: Proceedings of 'Methods
in Dialectology' XI, Joensuu (Finland). PDF,
14 pages.
2004
- Forst, Martin, Núria Bertomeu, Berthold Crysmann, Frederik Fouvry, Silvia Hansen-Schirra,
Valia Kordoni (2004):
Towards a dependency-based gold standard for German parsers - The TiGer Dependency Bank. In Proceedings of the COLING Workshop on Linguistically Interpreted
Corpora (LINC '04), Geneva (Switzerland). PDF, 7
pages.
- Fortmann, Christian, Martin Forst (2004): An LFG
grammar checker for CALL, In Proceedings of
ICALL-2004, Venice (Italy). PDF, 4
pages.
- Siebenhaar, Beat, Martin Forst & Eric Keller
(2004): Timing in Bernese and Zurich German. What the Development of a
Dialectal Speech Synthesis System Tells us about
it. In Peter Gilles & Jörg Peters (eds.): Regional Variation in Intonation, Tübingen: Niemeyer Verlag (Linguistische Arbeiten).
2003
- Butt, Miriam,
Martin Forst, Tracy H. King & Jonas Kuhn (2003): The Feature Space in
Parallel Grammar Writing. In Proceedings
of ESSLLI'03 - Workshop on Ideas and Strategies in Multilingual Grammar
Development, Vienna (Austria). PDF,
8 pages.
- Cahill, Aoife, Martin Forst, Mairéad
McCarthy, Ruth O'Donovan, Christian Rohrer, Josef van Genabith
& Andy Way (2003): Treebank-Based Multilingual Unification Grammar
Development. In Proceedings of
ESSLLI'03 - Workshop on Ideas and Strategies in Multilingual Grammar
Development, Vienna (Austria). PDF, 8
pages.
- Forst, Martin
(2003): Treebank Conversion - Establishing a testsuite
for a broad-coverage LFG from the the
TIGER treebank. In Proceedings of the EACL Workshop on Linguistically Interpreted
Corpora (LINC '03), Budapest (Hungary). PDF, 8 pages.
- Forst, Martin
(2003): Treebank Conversion - Creating an f-structure bank from the TIGER
Corpus. In Proceedings
of the LFG03 Conference, Saratoga Springs (NY, USA). PDF, 12 pages.
2002
- Forst, Martin
(2002): La traduction
automatique dans le
cadre formel de la LFG - Un système
de traduction entre l'allemand
standard et le zurichois , CTL
No 41, Université de Lausanne.
Martin
Forst, mforst "at" parc
"dot" com
Last updated: